An intelligent data processing system for interior design
Through entropy weight method and CRF model, the importance and spatial layout of design elements are optimized, and the response problems of existing systems when dealing with complex user preferences and design needs is solved, the scientificity of the design and user satisfaction are improved, and the interior design is improved. efficiency and aesthetics.
Patent Information
- Application Number
- CN202411141925.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-08-20
AI Technical Summary
The existing intelligent data processing system for interior design is difficult to respond in a timely manner when dealing with complex user preferences and variable design needs, resulting in the design plan not meeting user expectations, and there is subjectivity in the judgment of the importance of design elements, affecting the objectivity of the design and Scientificity, thereby reducing the efficiency and aesthetics of the design.
The entropy weight method is used to calculate the information entropy value of the design element, adjust the importance of the design element through the weight configuration module, combine the CRF model training module to analyze the interdependence between the design elements, optimize the spatial layout and furniture position, and generate more in line with user needs. design plan.
By quantitatively analyzing the importance of design elements, we will improve the scientificity and accuracy of the design, optimize the functionality and aesthetics of the space, and improve user satisfaction and the efficiency of design solutions.
Smart Images

Figure CN118656906B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of data processing, and in particular to an intelligent data processing system for interior design. Background Art
[0002] The field of data processing includes the collection, storage, sorting, retrieval and transformation of data. Making data easier to access, manage and understand supports decision-making, optimizes business processes and enhances data insights. Data processing technology can be applied to a variety of scenarios, including business intelligence, cloud computing, big data analysis and the Internet of Things. Including database management systems, data mining technology, machine learning and various forms of data visualization, all are aimed at improving data processing efficiency and accuracy.
[0003] Among them, the intelligent data processing system for interior design is a technical solution specifically for the field of interior design, which assists the design process by using data processing and artificial intelligence technology. Its main uses include automated design layout, optimized space utilization, and simulated lighting and material effects. It improves design efficiency while reducing design errors, and optimizes design decisions through simulation and prediction results. In addition, by integrating project requirements, user preferences, and environmental data, the system can provide more personalized and accurate interior design solutions.
[0004] Although existing technologies are widely used in automated design layout and optimized space utilization, they are difficult to respond in a timely manner when dealing with complex user preferences and changing design requirements, resulting in the difficulty of generating design solutions that fully meet user expectations. In addition, existing systems rely on the designer's experience and judgment when analyzing the importance of design elements, which is subjective and affects the objectivity and scientific nature of the design. It is easy to overlook some design elements with potential value, which limits the exploration of innovative designs. As a result, the design solution has poor efficiency and aesthetics, which further affects user acceptance and satisfaction. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an intelligent data processing system for interior design.
[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an intelligent data processing system for interior design, the system comprising: a design element impact analysis module collects furniture size, layout scheme, material type, lighting data, color scheme, integrates to obtain an interior design data set, calculates the entropy value of each parameter, measures its influence in the overall design, and generates an element information entropy value;
[0007] The weight configuration module performs weight allocation on the design elements in the interior design data set according to their element information entropy values based on the element information entropy values, and generates a weight allocation result;
[0008] The feature integration module refers to the weight distribution result, integrates the spatial attributes of the interior design data set and the user's layout preferences, including size, shape and user preference information, to generate a feature data set;
[0009] The CRF model training module uses the feature data set to train the conditional random field model, optimizes the model prediction effect by identifying the interdependencies between the design elements, and generates an optimized CRF model;
[0010] The spatial layout analysis module uses the optimized CRF model to evaluate the spatial layout efficiency of the interior design data set, identifies improvement space by analyzing the utilization efficiency of each area, and generates spatial data analysis results;
[0011] The space layout optimization module adjusts and optimizes the space layout and furniture positions in the interior design data set according to the space data analysis results, and generates optimized interior layout information.
[0012] The present invention has the following improvements: the element information entropy value includes the space occupancy entropy value of each type of furniture, the reaction entropy values of multiple materials and the visual impact entropy value of each color scheme; the weight distribution result includes the furniture size weight, the layout scheme weight, the material selection weight, the light intensity weight and the color scheme weight; the feature data set includes: space dimension features, design style preference features and user behavior pattern features; the optimized CRF model includes a design element dependency analysis model and a layout efficiency optimization model; the spatial data analysis result includes functional area efficiency scores, space utilization and improvement measures; the optimized indoor layout information includes reconfigured furniture positions, optimized traffic paths and lighting layout.
[0013] The present invention is improved in that the design element impact analysis module includes:
[0014] The data collection submodule collects furniture size, layout plan, material type, lighting data, and color scheme, and integrates them to obtain the interior design data set;
[0015] The entropy value calculation submodule calculates the entropy value of each design parameter through the interior design data set by using the entropy weight method, records the entropy values of various data such as furniture size and material type, lists the entropy value indicators item by item, and obtains the entropy value data set;
[0016] The influence measurement submodule evaluates and records the entropy value of each design element based on the entropy value data set, analyzes the quantitative index of its influence on the overall design, and obtains the element information entropy value.
[0017] The present invention is improved in that the entropy weight method is according to the formula:
[0018] ,
[0019] Calculate the entropy value of each design parameter;
[0020] in, represents the entropy value, k is a constant used to standardize the entropy value, is the relative frequency of the i-th design parameter, For parameters The natural logarithm of is the material diversity entropy The weight coefficient of is the entropy value of the material type, is the color diversity entropy The weight coefficient of The entropy value for the color configuration, Light distribution entropy The weight coefficient of The entropy value set for lighting, is the spatial morphological entropy The weight coefficient of is the entropy value of the spatial form.
[0021] The present invention is improved in that the weight configuration module comprises:
[0022] The weight analysis submodule uses the element information entropy value, analyzes the entropy value to identify the priority of each design element, arranges the design elements according to the entropy value, and generates a weight priority list;
[0023] The weight adjustment submodule assigns a weight to each design element in the interior design data set based on the weight priority list, and the weight assignment reflects the influence of the entropy value of each element on the design to form an initial weight configuration;
[0024] The weight optimization submodule optimizes the weight of each design element based on the initial weight configuration, according to the current design requirements and user preferences, and obtains a weight distribution result.
[0025] The present invention is improved in that the feature integration module comprises:
[0026] The attribute aggregation submodule refers to the weight distribution result, collects and integrates the size and shape information of each space from the interior design dataset, and classifies and summarizes the space attribute information to form a space attribute dataset;
[0027] The preference analysis submodule collects user survey data, analyzes user preferences for furniture layout and design style, integrates the preference data with the interior design dataset, supplements user preference dimensions, and generates a preference information integration dataset;
[0028] The feature generation submodule integrates the data set based on the preference information, identifies key design features, including the optimization of furniture placement movement lines, maximization of space utilization, and user preference reflection, and generates a feature data set.
[0029] The present invention is improved in that the CRF model training module includes:
[0030] The feature preparation submodule performs feature screening and preprocessing operations based on the feature data set to generate sorted feature data;
[0031] The dependency analysis submodule uses the collated feature data to construct a conditional random field model to analyze the interdependencies between design elements, i.e., the influence of furniture position, space shape, material selection and user layout preference on space layout effect and user experience, and generates element relationship analysis results;
[0032] The model optimization submodule adjusts and optimizes the parameters and structure of the conditional random field model based on the element relationship analysis results to obtain an optimized CRF model.
[0033] The present invention is improved in that the conditional random field model is according to the formula:
[0034] ,
[0035] Conduct interdependency analysis among design elements;
[0036] in, is the conditional probability of outputting label sequence y given the input feature vector x, where x is the input feature vector and y is the output label sequence. is the sequence of all tags, is the characteristic function, used to calculate the given before and after states and and the weight contribution when inputting x, is the learned weight parameter, i represents the position in the sequence, and j is used to index the feature function.
[0037] The present invention is improved in that the spatial layout analysis module comprises:
[0038] The layout effect evaluation submodule evaluates the overall spatial layout effect of the interior design dataset based on the optimized CRF model, analyzes the impact of each design element, including furniture location and space usage, on the overall layout, and generates spatial layout analysis results;
[0039] The regional utilization analysis submodule uses the spatial layout analysis results to analyze the spatial utilization effect of each region, identifies the performance of each region by comparing the effectiveness of multiple regional functions and layouts, and generates functional area analysis results;
[0040] The improved area identification submodule identifies the area that needs to be improved or redesigned through the functional area analysis results to obtain spatial data analysis results.
[0041] The present invention is improved in that the space layout optimization module comprises:
[0042] The layout adjustment submodule iteratively adjusts the spatial layout in the interior design data set based on the spatial data analysis results, analyzes the fluidity and functionality of the current layout, reorganizes the space, and generates an adjusted layout plan;
[0043] The furniture position optimization submodule adopts the adjusted layout scheme, adjusts the positions of furniture and decorations with reference to the flow of people and the visual balance of the space, and generates an optimized furniture layout;
[0044] The layout verification submodule simulates the functionality and aesthetics of the layout according to the optimized furniture layout, and generates optimized indoor layout information.
[0045] Compared with the prior art, the advantages and positive effects of the present invention are:
[0046] In the present invention, the entropy weight method is used to quantitatively analyze the information entropy of interior design elements such as furniture layout, light intensity and color matching, so that designers can accurately judge the importance of each element and adjust its weight accordingly, thereby improving the scientificity and accuracy of the design. Through automated weight adjustment, designers can more objectively optimize the functionality and aesthetics of the space and effectively improve the efficiency of space use. In addition, through the CRF model, the system can intelligently recommend the space layout plan that best suits the user's needs by integrating the user's historical layout preferences and functional requirements, which not only improves user satisfaction, but also optimizes the practicality and comfort of the space. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 A module diagram of an intelligent data processing system for interior design is proposed for the present invention;
[0048] Figure 2 The present invention proposes a system framework diagram of an intelligent data processing system for interior design;
[0049] Figure 3 A schematic diagram of a design element impact analysis module of the present invention;
[0050] Figure 4A schematic diagram of a weight configuration module of the present invention;
[0051] Figure 5 It is a schematic diagram of the characteristic integration module of the present invention;
[0052] Figure 6 Schematic diagram of the CRF model training module of the present invention;
[0053] Figure 7 is a schematic diagram of a spatial layout analysis module of the present invention;
[0054] Figure 8 It is a schematic diagram of the spatial layout optimization module of the present invention. DETAILED DESCRIPTION
[0055] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0056] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.
[0057] See also Figure 1 ,The present invention provides a technical solution: an intelligent data processing system for interior design, the system includes ,a design element impact analysis module collects furniture size, layout scheme, material type, lighting data, and color scheme, ,integrates to obtain an interior design data set, calculates the entropy value of each parameter, ,measures its influence in the overall design, and generates the element information entropy value;
[0058] The weight configuration module assigns weights to the design elements in the interior design data set based on their element information entropy values and generates weight assignment results;
[0059] The feature integration module refers to the weight distribution results, integrates the spatial attributes of the interior design dataset and the user's layout preferences, including size, shape and user preference information, to generate a feature dataset;
[0060] The CRF model training module uses the feature data set to train the conditional random field model, optimizes the model prediction effect by identifying the interdependencies between design elements, and generates an optimized CRF model;
[0061] The spatial layout analysis module uses the optimized CRF model to evaluate the spatial layout efficiency of the interior design dataset, identifies improvement spaces by analyzing the utilization efficiency of each area, and generates spatial data analysis results;
[0062] The space layout optimization module adjusts and optimizes the space layout and furniture positions in the interior design dataset according to the spatial data analysis results, and generates optimized interior layout information.
[0063] The element information entropy values include the space occupancy entropy of each type of furniture, the reaction entropy of multiple materials, and the visual impact entropy of each color scheme. The weight distribution results include furniture size weight, layout scheme weight, material selection weight, light intensity weight, and color scheme weight. The feature data set includes: spatial dimension characteristics, design style preference characteristics, and user behavior pattern characteristics. The optimized CRF model includes a design element dependency analysis model and a layout efficiency optimization model. The spatial data analysis results include functional area efficiency scores, space utilization, and improvement measures. The optimized indoor layout information includes reconfigured furniture positions, optimized traffic paths, and lighting layout.
[0064] See also Figure 2 and Figure 3 , the design element impact analysis module includes:
[0065] The data collection submodule collects furniture size, layout plan, material type, lighting data, and color scheme, and the process of integrating them to obtain the interior design data set is as follows;
[0066] In the design element impact analysis module, the data collection submodule first collects key data, such as furniture size, layout plan, material type, lighting data and color scheme. This includes measuring the three-dimensional dimensions of each piece of furniture, recording the physical and chemical properties of various materials, such as hardness and reflectivity, and the type (natural or artificial) and intensity (lumen value) of the light source. In addition, the color scheme is collected, including the RGB value of the color and the frequency of use. These data are systematically integrated into an interior design data set to provide basic data support for subsequent analysis.
[0067] The entropy value calculation submodule uses the entropy weight method to calculate the entropy value of each design parameter through the interior design data set, records the entropy values of various data such as furniture size and material type, and lists the entropy value indicators item by item. The process of obtaining the entropy value data set is as follows;
[0068] By determining the frequency of occurrence of each design parameter in the data set. To this end, the module counts the number of occurrences of each parameter in the entire data set. The statistical results reflect the frequency of use of each design element in the space design, providing basic data for further entropy calculation. In this way, the module is able to quantify the information abundance of each parameter in the design, which is also a key factor in evaluating its impact on the overall design.
[0069] The entropy weight method is based on the formula:
[0070] ,
[0071] Calculate the entropy value of each design parameter;
[0072] in, It represents the entropy value, which is used to comprehensively evaluate the diversity and balance in interior design, taking into account more design dimensions. k is a constant, which is used to standardize the entropy value so that its maximum value is 1, keeping the original purpose unchanged. is the relative frequency of the i-th design parameter, which is obtained by counting the ratio of the number of times the parameter appears in the total data set to the total number of times. For parameters The natural logarithm of is used to calculate the amount of information in the entropy value. is the material diversity entropy The weight coefficients are determined through data analysis to optimize the entropy value's ability to reflect design diversity. It is the entropy value of material type, which evaluates the diversity of material selection and reflects the frequency and diversity of use of different material types in design. is the color diversity entropy The weight coefficient is determined through data analysis. An entropy value assigned to a color to assess the diversity of color usage, including the distribution and variation of various color schemes in a design. Light distribution entropy The weight coefficient is determined through data analysis. The entropy value set for lighting, used to evaluate the diversity of lighting intensity and distribution, including changes in different light sources and lighting effects. is the spatial morphological entropy The weight coefficient is determined through data analysis. It is the entropy value of spatial morphology, which is used to evaluate the diversity of spatial layout and shape, including different spatial configurations and layout schemes.
[0073] The calculation process is as follows:
[0074] Extract each design parameter from the design dataset This involves counting the number of times each design element appears in the entire data set and then dividing it by the total number of elements to get the relative frequency.
[0075] ,
[0076] in:
[0077] is the number of occurrences of the i-th design parameter. N is the total number of parameters. For each parameter, calculate its information content, that is: .
[0078] Calculate the entropy of the newly added parameters For each newly added parameter (material diversity , Color diversity , Light distribution , spatial form ), the calculation process is as follows:
[0079] Material diversity :
[0080] Collect all data about material types from the dataset. For each material type, calculate its frequency of occurrence .
[0081] The material diversity entropy is calculated using the entropy formula:
[0082] ,
[0083] Color Variety :
[0084] Collect usage data for all color schemes. Calculate the frequency of each color scheme . Calculate the color diversity entropy:
[0085] ,
[0086] Light distribution :
[0087] Collect data for different lighting settings. Calculate the frequency for each lighting setting .
[0088] Calculate the illumination distribution entropy:
[0089] ,
[0090] Spatial form :
[0091] Analyze data of different spatial patterns. Calculate the frequency of each pattern .
[0092] Calculate spatial morphological entropy: ,
[0093] Integrate all calculated entropy values into the entropy calculation formula:
[0094] ,
[0095] The calculated entropy value It not only reflects the traditional information abundance of design elements, but also takes into account the diversity of materials, colors, lighting and spatial forms. This comprehensive entropy value enables designers to more comprehensively evaluate the diversity and balance of interior design solutions, help optimize design decisions, and enhance the innovation of design solutions and user satisfaction.
[0096] The influence measurement submodule evaluates and records the entropy value of each design element based on the entropy data set, analyzes the quantitative indicators of its impact on the overall design, and obtains the element information entropy value in the following process;
[0097] Based on the entropy value of each design element , the weight of each element is calculated using the following formula , where the entropy is exponentially scaled to emphasize the influence of high entropy elements: ,in, represents the entropy value of a single design element, is a coefficient greater than 1, which is used to enhance the weight of high entropy elements and emphasize their leading role in the design. It represents the sum of the entropy values of all elements, emphasizing the comprehensive impact of the overall design. In this way, the contribution of each design element to the overall interior design can be quantitatively evaluated, and the element information entropy value can be finally obtained. This process not only simplifies the measurement of the influence of elements, but also makes design decisions more data-driven, ensuring that each design decision is fully supported by information.
[0098] See also Figure 2 and Figure 4 , the weight configuration module includes:
[0099] The weight analysis submodule uses the element information entropy value, analyzes the entropy value to identify the priority of each design element, and arranges the design elements according to the entropy value. The process of generating a weight priority list is as follows;
[0100] By using the element information entropy value, the importance of each design element is systematically analyzed to determine its priority. The specific operation includes all elements according to their entropy value. Sorting is done in descending order to ensure that elements with higher entropy values are given higher priority. The entropy values of all elements are compared one by one and a weighted priority list is generated based on this, which clearly shows the order of arrangement from the most important to the least important elements.
[0101] The weight adjustment submodule assigns weights to each design element in the interior design dataset based on the weight priority list. The weight assignment reflects the impact of the entropy value of each element on the design. The process of forming the initial weight configuration is as follows;
[0102] Based on the generated weight priority list, each design element is weighted. During the weighting process, the weighting formula is used: ,in is the adjusted weight of element i, is the entropy value of element i, is the entropy rank of element i (e.g., the element with the highest entropy is ranked 1, the second highest is ranked 2, and so on), This configuration ensures that the weight of the element is proportional to its influence on the design, forming the initial weight configuration.
[0103] The weight optimization submodule optimizes the weight of each design element based on the initial weight configuration according to the current design requirements and user preferences, and the process of obtaining the weight distribution result is as follows;
[0104] The initial weight configuration is optimized according to the current design requirements and user preferences. During the optimization process, the adjustment formula is used: ,in is the final optimized weight of element i, is the initial adjusted weight calculated by entropy and ranking, is the weight set according to user preference, and It is an adjustment coefficient between 0 and 1, which is used to balance the professionalism of the design with the personalized needs of the users.
[0105] See also Figure 2 and Figure 5 , the feature integration module includes:
[0106] The attribute aggregation submodule refers to the weight distribution result, collects and integrates the size and shape information of each space from the interior design dataset, and classifies and summarizes the spatial attribute information to form the spatial attribute dataset as follows;
[0107] The length, width, and height of the room are measured, and the location of windows and doors is recorded. Shape information involves the geometric layout of the room, such as whether it is rectangular, L-shaped, or other shapes. In addition, attribute aggregation also takes into account other spatial characteristics such as wall material and floor type. All of this data is combined through an algorithm to calculate the overall functionality and aesthetics score of the space. , the calculation formula is: ,in, It is the overall functionality and aesthetics rating of the space. L, W, H represent the numerical ratings of the length, width, and height of the room, respectively. Represents scores for other functional factors such as light and ventilation. , , , is the weight coefficient of each factor. Represents the weighted sum of all other functional factors.
[0108] The preference analysis submodule collects user survey data, analyzes user preferences for furniture layout and design style, integrates the preference data with the interior design dataset, supplements the user preference dimensions, and generates a preference information integration dataset in the following process;
[0109] Using user feedback, we evaluate the popularity of different furniture and layout options and identify patterns in user preferences by analyzing the data. Based on these patterns, we use a preference weighting formula The designs were scored, where is the comprehensive score in the preference dataset. Is the identifier of the preference item. is the user evaluation value of the preference item. Represents the weighted sum of all preference items.
[0110] The feature generation submodule integrates the data set based on the preference information and identifies key design features, including the optimization of furniture placement, maximization of space utilization, and user preference reflection. The process of generating the feature data set is as follows;
[0111] By analyzing the spatial size, shape and user preference data sets, key features are extracted and the design is optimized. Use feature generation formula ,in, is the final feature dataset score. Indicates the score of traffic flow optimization and space utilization efficiency. , , It is the weight coefficient of each factor, which adjusts the influence of space functionality, user preference and traffic flow optimization in the total score. It improves the efficiency of interior design.
[0112] See also Figure 2 and Figure 6 , the CRF model training module includes:
[0113] The feature preparation submodule performs feature screening and preprocessing operations based on the feature data set, and the process of generating the sorted feature data is as follows;
[0114] Feature screening involves analyzing the data frequency and range of each design element. During the screening process, the variance of each feature will be calculated to determine its degree of variation. If the variance is lower than the preset threshold, the feature is considered to contribute less to the model and should be eliminated. Preprocessing includes normalizing continuous variables and scaling all features to the same scale to ensure the effectiveness of model training. For categorical variables, one-hot encoding will be applied to convert them into numerical data so that the model can be parsed. The formula is: ,in, represents the normalized eigenvalue, represents the original eigenvalue, and represent the mean and standard deviation of the features respectively.
[0115] The dependency analysis submodule uses the sorted feature data to construct a conditional random field model to analyze the interdependencies between design elements, namely the impact of furniture position, space shape, material selection, and user layout preference on space layout effects and user experience. The process of generating element relationship analysis results is as follows;
[0116] In this process, the conditional probabilities between different design elements are calculated by evaluating the contribution of each element to the overall design satisfaction, the contribution value of each element is determined through data collection, and these values are input into the conditional random field model.
[0117] The conditional random field model follows the formula:
[0118] ,
[0119] Conduct interdependency analysis among design elements;
[0120] in, is the conditional probability of outputting the label sequence y given the input feature vector x; x is the input feature vector, which contains all relevant feature information used for model prediction, such as furniture size, material type, etc.; y is the output label sequence, which represents the state or category of each design element predicted by the model based on the input x; is the sequence of all tags, used for normalization calculation, to ensure is a valid probability value; is the characteristic function, used to calculate the given before and after states and And the weight contribution when inputting x; is the learned weight parameter, corresponding to the characteristic function The weights of the model can be adjusted to optimize the predictive performance of the model; i represents the position in the sequence and is used to track the order of elements in the output sequence; j is used to index the feature function, allowing the model to distinguish and optimize various factors that affect the interaction between design elements.
[0121] In the CRF model, the feature function Indicates the state of the labels before and after the i-th position , The association with the input x. It is learned from the training data in a data-driven way. For example, the feature function can be defined by counting the frequency of occurrence of various label combinations.
[0122] Calculation of weight parameters Weight parameters The calculation of usually involves a gradient ascent (or descent) method to optimize the likelihood function.
[0123] The calculation process is as follows:
[0124] Initialization parameters: Setting The initial value of , usually 0 or a small random number.
[0125] Calculate the gradient: For each parameter , calculate its gradient , the gradient expression depends on the characteristic function and the current parameter value, specifically:
[0126] ,
[0127] in, Indicates the expected value of the corresponding feature under the current model parameters.
[0128] Using Gradients and Learning Rates Update parameters:
[0129] ,
[0130] here, is the step size, which controls the learning rate.
[0131] The iterative process of model training repeats the above steps of calculating gradients and updating parameters until the convergence condition is reached, usually when the change in parameters is less than a certain threshold or the maximum number of iterations is reached.
[0132] The calculation results of the CRF model can more accurately predict the interdependence of design elements. It can help designers understand how different design decisions affect the spatial layout effect and user experience, so as to make more reasonable design choices.
[0133] The model optimization submodule adjusts and optimizes the parameters and structure of the conditional random field model based on the results of element relationship analysis, and the process of obtaining the optimized CRF model is as follows;
[0134] By analyzing the element relationship analysis results of the feature data set, the parameters with greater influence in the model are adjusted and the model structure is optimized to improve the prediction accuracy and processing speed. The weight calculation formula will be applied: ,in, and Represent the parameter weights before and after adjustment, represents the learning rate, Represents the weight update value during the gradient descent process, which is calculated by comparing the performance of the model on the training data.
[0135] See also Figure 2 and Figure 7 , the spatial layout analysis module includes:
[0136] The layout effect evaluation submodule evaluates the overall spatial layout effect of the interior design dataset based on the optimized CRF model, analyzes the impact of each design element, including furniture location and space usage, on the overall layout, and generates the spatial layout analysis results as follows;
[0137] For each design element, such as furniture location and space usage, calculate its correlation coefficient with user satisfaction These coefficients are calculated by collecting user feedback and space usage data, and then using this data to update the CRF model to more accurately predict the spatial layout effect. The formula is: ,in, represents the spatial layout score, is the correlation coefficient between the kth design element and user satisfaction, is the frequency of use of the element.
[0138] The regional utilization analysis submodule uses the spatial layout analysis results to analyze the spatial utilization effect of each region. By comparing the effectiveness of multiple regional functions and layouts, the performance of each region is identified. The process of generating functional area analysis results is as follows;
[0139] For each region, the utilization It is calculated by the ratio of actual activity time to area availability time, while user satisfaction is obtained through regular user satisfaction surveys. These data will be aggregated to form a comprehensive score to identify areas of outstanding performance or areas that need improvement. The calculation formula is: ,in, Represents the regional performance score, is the area utilization rate, is the user satisfaction index, and is the weight coefficient of these two indicators.
[0140] The improvement area identification submodule identifies the areas that need to be improved or redesigned through the functional area analysis results, and the process of obtaining the spatial data analysis results is as follows;
[0141] Based on the regional performance score, identify the areas with low efficiency or user dissatisfaction. By integrating multi-dimensional data, such as past design feedback, current usage data, and user satisfaction surveys, the comprehensive performance index of each area is calculated. The formula is adjusted as follows: ,in, represents the improvement index, is the adjustment factor used to weight the difference between the current score and the standard score, T is the target performance score, is the current score of the area. Areas with a score below this will be marked as needing improvement.
[0142] See also Figure 2 and Figure 8 , the spatial layout optimization module includes:
[0143] The layout adjustment submodule iteratively adjusts the spatial layout in the interior design dataset based on the spatial data analysis results, analyzes the fluidity and functionality of the current layout, reorganizes the space, and generates the adjusted layout plan in the following process;
[0144] Mobility analysis is performed by calculating the intersection of traffic lines and the density of people flow in the space. Using the density function , indicating that in the coordinate The density of pedestrian flow is combined with functional evaluation, and the frequency of use of each functional area and user feedback are counted to measure it. These data are analyzed, and various layout adjustment schemes are simulated to optimize space utilization efficiency and user satisfaction. The formula is: ,in, represents the new layout efficiency score, is the liquidity score, is a functional score, and is the weight coefficient of liquidity and functionality.
[0145] The furniture position optimization submodule adopts the adjusted layout plan, adjusts the position of furniture and decorations with reference to the flow of people and the visual balance of the space, and generates the optimized furniture layout in the following process;
[0146] Using the traffic flow model To evaluate the impact of furniture layout on pedestrian flow, and combine the principle of visual balance, by calculating the visual guide line and visual center of gravity , to optimize the furniture position. The calculation formula is: ,in, Represents the optimization score of the furniture layout, is the furniture layout's support score for human flow, is the visual balance score, and is the weight of these two assessments, Represents the dynamic line model, It is a visual guide line. It is the visual center of gravity.
[0147] The layout verification submodule simulates the functionality and aesthetics of the layout based on the optimized furniture layout, and the process of generating optimized indoor layout information is as follows;
[0148] Simulate the environment by creating a layout , insert various design elements into it, and make the layout more practical. and aesthetics The composite scoring method is used to combine functionality and aesthetics into an overall score. The calculation formula is as follows: ,in, Represents the final layout score, and Represents the functionality and aesthetics scores, and is the corresponding weight coefficient, Represents a simulated environment.
[0149] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. An intelligent data processing system for interior design, characterized in that: The system comprises: The design element impact analysis module collects furniture size, layout plan, material type, lighting data, and color scheme, integrates them to obtain the interior design data set, calculates the entropy value of each parameter, measures its influence in the overall design, and generates the element information entropy value; The design element impact analysis module includes: The data collection submodule collects furniture size, layout plan, material type, lighting data, and color scheme, and integrates them to obtain the interior design data set; The entropy value calculation submodule calculates the entropy value of each design parameter through the interior design data set by using the entropy weight method, records the entropy values of various data such as furniture size and material type, lists the entropy value indicators item by item, and obtains the entropy value data set; The influence measurement submodule evaluates and records the entropy value of each design element based on the entropy value data set, analyzes the quantitative index of its influence on the overall design, and obtains the element information entropy value; The entropy weight method is based on the formula: , Calculate the entropy value of each design parameter; in, represents the entropy value, k is a constant used to standardize the entropy value, is the relative frequency of the i-th design parameter, For parameters The natural logarithm of is the material diversity entropy The weight coefficient of is the entropy value of the material type, is the color diversity entropy The weight coefficient of The entropy value for the color configuration, Light distribution entropy The weight coefficient of The entropy value set for lighting, is the spatial morphological entropy The weight coefficient of is the entropy value of the spatial morphology; The weight configuration module performs weight allocation on the design elements in the interior design data set according to their element information entropy values based on the element information entropy values, and generates a weight allocation result; The feature integration module refers to the weight distribution result, integrates the spatial attributes of the interior design data set and the user's layout preferences, including size, shape and user preference information, to generate a feature data set; The CRF model training module uses the feature data set to train the conditional random field model, optimizes the model prediction effect by identifying the interdependencies between the design elements, and generates an optimized CRF model; The spatial layout analysis module uses the optimized CRF model to evaluate the spatial layout efficiency of the interior design data set, identifies improvement space by analyzing the utilization efficiency of each area, and generates spatial data analysis results; The space layout optimization module adjusts and optimizes the space layout and furniture positions in the interior design data set according to the space data analysis results, and generates optimized interior layout information.
2. The intelligent data processing system for interior design according to claim 1, characterized in that: The element information entropy value includes the space occupancy entropy value of each type of furniture, the reaction entropy values of multiple materials and the visual impact entropy value of each color scheme; the weight distribution result includes the furniture size weight, layout scheme weight, material selection weight, light intensity weight and color scheme weight; the feature data set includes: spatial dimension features, design style preference features and user behavior pattern features; the optimized CRF model includes a design element dependency analysis model and a layout efficiency optimization model; the spatial data analysis result includes functional area efficiency scores, space utilization and improvement measures; the optimized indoor layout information includes reconfigured furniture positions, optimized traffic paths and lighting layout.
3. The intelligent data processing system for interior design according to claim 1, characterized in that: The weight configuration module includes: The weight analysis submodule uses the element information entropy value, analyzes the entropy value to identify the priority of each design element, arranges the design elements according to the entropy value, and generates a weight priority list; The weight adjustment submodule assigns a weight to each design element in the interior design data set based on the weight priority list, and the weight assignment reflects the influence of the entropy value of each element on the design to form an initial weight configuration; The weight optimization submodule optimizes the weight of each design element based on the initial weight configuration according to current design requirements and user preferences to obtain a weight distribution result.
4. The intelligent data processing system for interior design according to claim 1, characterized in that: The feature integration module comprises: The attribute aggregation submodule refers to the weight distribution result, collects and integrates the size and shape information of each space from the interior design dataset, and classifies and summarizes the space attribute information to form a space attribute dataset; The preference analysis submodule collects user survey data, analyzes user preferences for furniture layout and design style, integrates the preference data with the interior design dataset, supplements user preference dimensions, and generates a preference information integration dataset; The feature generation submodule integrates the data set based on the preference information, identifies key design features, including the optimization of furniture placement movement lines, maximization of space utilization, and user preference reflection, and generates a feature data set.
5. The intelligent data processing system for interior design according to claim 1, characterized in that: The CRF model training module includes: The feature preparation submodule performs feature screening and preprocessing operations based on the feature data set to generate sorted feature data; The dependency analysis submodule uses the collated feature data to construct a conditional random field model to analyze the interdependencies between design elements, i.e., the influence of furniture position, space shape, material selection and user layout preference on space layout effect and user experience, and generates element relationship analysis results; The model optimization submodule adjusts and optimizes the parameters and structure of the conditional random field model based on the element relationship analysis results to obtain an optimized CRF model.
6. The intelligent data processing system for interior design according to claim 5, characterized in that: The conditional random field model is based on the formula: , Conduct interdependency analysis among design elements; in, is the conditional probability of outputting label sequence y given the input feature vector x, where x is the input feature vector and y is the output label sequence. is the sequence of all tags, is the characteristic function, used to calculate the given before and after states and and the weight contribution when inputting x, is the learned weight parameter, i represents the position in the sequence, and j is used to index the feature function.
7. The intelligent data processing system for interior design according to claim 1, characterized in that: The spatial layout analysis module includes: The layout effect evaluation submodule evaluates the overall spatial layout effect of the interior design dataset based on the optimized CRF model, analyzes the impact of each design element, including furniture location and space usage, on the overall layout, and generates spatial layout analysis results; The regional utilization analysis submodule uses the spatial layout analysis results to analyze the spatial utilization effect of each region, identifies the performance of each region by comparing the effectiveness of multiple regional functions and layouts, and generates functional area analysis results; The improved area identification submodule identifies the area that needs to be improved or redesigned through the functional area analysis results to obtain spatial data analysis results.
8. The intelligent data processing system for interior design according to claim 1, characterized in that: The space layout optimization module includes: The layout adjustment submodule iteratively adjusts the spatial layout in the interior design data set based on the spatial data analysis results, analyzes the fluidity and functionality of the current layout, reorganizes the space, and generates an adjusted layout plan; The furniture position optimization submodule adopts the adjusted layout scheme, adjusts the positions of furniture and decorations with reference to the flow of people and the visual balance of the space, and generates an optimized furniture layout; The layout verification submodule simulates the functionality and aesthetics of the layout according to the optimized furniture layout, and generates optimized indoor layout information.
